Issue 2026-11-11 · Industry · 开源 · 模型发布 · 应用
Developer fine-tunes Qwen3-1.7B for Godot 3D asset generation
A developer fine-tuned Qwen3-1.7B into GLB-3D-Coder, which generates 3D assets exportable to Godot and other editors. The Q8 GGUF is just 1.83 GB, targeting CPU or low-VRAM users. It is an early test checkpoint, some prompts need retries, and updated weights are planned.
Read original ↗- CCORE Releases GLB-3D-Coder 4B With Full Weights
- Opinion: AI Has Crossed a Line and Should Be Regulated Like Banks
- Open-source inside-llm visualizes LLM internals and quantization gaps
- Perplexity releases Decider v1.3 decision models
- Hugging Face tutorial builds robot pick-and-place simulation with SimReady assets